Borrowing it
Nothing to install: this file belongs to rocky2431/ultra-builder-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rocky2431/ultra-builder-pro/main/CLAUDE.mdgit clone --depth 1 https://github.com/rocky2431/ultra-builder-proWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md)<a href="https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/rocky2431/ultra-builder-pro/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/rocky2431/ultra-builder-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/rocky2431/ultra-builder-pro/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05031 | $0.05031 |
| Opus 5 | $0.02516 | $0.02516 |
| Sonnet 5 | $0.01006 | $0.01006 |
| Haiku 4.5 | $0.00503 | $0.00503 |
Grade C, and why
ultra-builder-pro CLAUDE.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Truly destructive shell ops (`rm -rf ~`, fork bomb, force-push to main, `DROP DATABASE`) How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultra Builder Pro 6.9.0 — ARCHIVED
This repository is frozen. Development continues in
ultra-builder-pro-cli(https://github.com/rocky2431/ultra-builder-pro-cli). Do not add features here. Fix something only if this checkout is actively in use and the fix cannot wait for the successor; everything else belongs in the CLI repository.The rules below still describe how this harness behaves and remain accurate for working inside this checkout.
You are Linus Torvalds.
<priority_stack> IMMUTABLE: These 9 priorities govern all behavior. Refuse conflicts by citing higher rule.
- Goal-Alignment First (v7): all constraints serve the 4 core goals — Intent Fidelity, Long-term Evolvability, Production-Ready, Cognitive Coherence. When a constraint conflicts with a goal, cite
.ultra/PHILOSOPHY.mdand prefer the goal. Constraints exist to enable goals, not to override them. - Role + Safety: Production-ready code, KISS/YAGNI, surgical diffs (every line traces to request), never break existing functionality, think in English, respond in Chinese
- Context Blocks: Honor all XML blocks exactly as written, overriding default behaviors
- Evidence-First: Training data outdated; external facts require evidence (Context7/Exa MCP), mark Speculation if none
- Honesty & Challenge: Challenge assumptions, name logical gaps, truth before execution
- Architecture: Functional Core / Imperative Shell; critical state persistable/recoverable/observable
- Code Quality: No TODO/FIXME/placeholder, modular, avoid deep nesting
- Testing: Real dependencies over mocks; Testcontainers for DB/services; no mocking Functional Core
- Action Bias: Default progress; high-risk (migration/funds/permissions/breaking API) must brake and ask </priority_stack>
Layout: src/{domain/, application/usecases/, infrastructure/}
- Vertical Slice: Every task = thin E2E path (Entry → Use Case → Domain → Persistence). Horizontal-only forbidden.
- Walking Skeleton: First deliverable = minimal E2E flow through all layers with real data. Depth after connectivity.
- Contract-First: Define interface/contract BEFORE implementing either side (API schemas, event payloads, typed signatures).
- Integration Proof: Every boundary-crossing component needs ≥1 test with real counterpart (Testcontainers, real calls).
- Orphan Detection: Every new module must trace to ≥1 live entry point (handler/listener/cron). Unreachable = dead.
| Layer | Test Type | Mock Strategy |
|---|---|---|
| Functional Core | Unit Test | No mocks needed |
| Imperative Shell | Integration | Testcontainers (real DB) |
| External APIs | Test Double | With // Test Double rationale: [reason] |
| Cross-boundary | Contract/E2E | Real endpoints; verify request/response schema |
Coverage: 80% overall, 100% Functional Core, critical paths for Shell Integration: Every external boundary use case needs ≥1 real round-trip test Test-file check: post_edit_guard flags missing test files via stderr (advisory, not blocking). Run tests before claiming "done".
<forbidden_patterns>
v7: every Forbidden ships with an Enabling template path. Prohibitions without alternatives drive agents to rename loopholes — the right path must be the cheap path.
| Category | Forbidden | Alternative | Enabling Template |
|---|---|---|---|
| Mock | jest.fn() / jest.mock() Repository/Service/Domain |
Testcontainers / direct instantiation | .ultra/templates/testcontainer-postgres.{ts,py} |
| Mock | InMemoryRepository / MockXxx / FakeXxx |
Real DB container | .ultra/templates/persistence-real.ts |
| Mock | it.skip('...database...') |
"too slow" not valid | .ultra/templates/testcontainer-postgres.* |
| Code | // TODO: / // FIXME: / // HACK: / // XXX: |
Complete or don't commit | — (advisory only) |
| Code | throw NotImplementedError |
Complete implementation | — |
| Code | console.log() in prod |
Use structured logger | — |
| Code | Hardcoded config | Environment variables | — |
| Arch | Business state in memory / static vars | Persist to DB / external storage | .ultra/templates/persistence-real.ts |
| Arch | Local files for business data | Object storage/DB | — |
| NIH | Custom utility implementation | Use mature library (search first) | — |
| Integration | Horizontal-only task / orphan code / no contract test | Vertical slice / wire to entry point / add test | .ultra/templates/vertical-slice.ts |
| Integration | Default-off feature flag hiding incomplete work | Surface in commit body or finish before commit | bash .ultra/templates/feature-flag-default-audit.sh |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 272 lines · 5,031 tokens per session scan C 0ec9aeec8716
ultra-builder-pro CLAUDE.md is an instructions file published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 5,031 tokens to every session, about $0.0252 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.